© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 248889
    Prev
    Next
    INDEX
    Explanations

    places, countries, and specific items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    0.48
    entire
    0.44
     thereof
    0.43
     。
    0.42
    <0xAA>
    0.41
    <0xA4>
    0.41
    <0xA7>
    0.41
    iv
    0.41
    wab
    0.40
    pti
    0.39
    POSITIVE LOGITS
     dictators
    0.50
    ឡិច
    0.46
    などの
    0.43
    等の
    0.43
     ಸೇರಿದ
    0.43
     nevoia
    0.42
     rebell
    0.42
    等地
    0.42
     diverge
    0.41
    ImageAlign
    0.41
    Activations Density 0.161%

    No Known Activations